Alibaba/Dense

AlibabaQwen 1.5 0.5B

Alibaba's tiny Qwen. Fast for basic tasks on minimal hardware.

chat
0.5B
Parameters
32K
Context length
7
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2024-02-04
Layers
24
KV Heads
16
Head Dim
64
Family
qwen

Quantization Options

QuantBitsVRAMQuality
Q4_K_M4.890.8 GBgood
Q5_K_S5.570.8 GBgood
Q5_K_M5.70.8 GBgood
Q6_K6.560.9 GBexcellent
Q8_08.51.0 GBlossless
FP16161.5 GBlossless

Select your GPU above to see speed estimates and compatibility for each quantization.

READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN QWEN 1.5 0.5B NOW

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (7)

IFEval31.5
MATH10.3
BigCodeBench8.8
BBH8.2
MMLU-PRO8.0
MUSR1.4
GPQA1.2

Run this model

Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run qwen:0.5b-q4_K_M

Downloads and runs automatically. Add --verbose for speed stats.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Find the best GPU for Qwen 1.5 0.5B

Build Hardware for Qwen 1.5 0.5B

Alibaba's tiny Qwen. Fast for basic tasks on minimal hardware.

▸ SPEC SHEET

Qwen 1.5 0.5B0.5B Dense.

▸ SPECIFICATIONS
PARAMETERS
0.5B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
32K tokens
CAPABILITIES
chat
RELEASE DATE
2024-02-04
PROVIDER
Alibaba
FAMILY
qwen
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.890.8 GB94%
Q5_K_S5.570.8 GB96%
Q5_K_M5.70.8 GB96%
Q6_K6.560.9 GB97%
Q8_08.51.0 GB100%
FP16161.5 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO8.0
MATH10.3
IFEval31.5
BBH8.2
GPQA1.2
MUSR1.4
BigCodeBench8.8
§ 02RUN COMMAND

Run Qwen 1.5 0.5B locally with Ollama — needs 0.8 GB VRAM at Q4_K_M:

$ollama run qwen:0.5b